Sentence generation apparatus

Abstract

To provide a sentence generation apparatus configured to easily create a sentence which indicates tendency of a person.SOLUTION: A sentence generation apparatus includes: an answer extraction unit which extracts answer results for an answer item to a question item that meets a second condition, from among answer items included in questionnaire results from answerers that meet a first condition, out of answer results of a questionnaire conducted to a plurality of answerers; and a sentence generation unit which generates a sentence which indicates tendencies of the answerers that meet the first condition, in accordance with the answer results extracted by the answer extraction unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a sentence generation device. [Background technology]

[0002] Conventionally, in marketing, personas are created when analyzing the profile of a target person. For example, one technique for creating such personas uses information from social networking sites (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2023-89233 Summary of the Invention [Problem to be solved by the invention]

[0004] However, creating an accurate persona using sentences that indicate a person's tendencies is difficult and time-consuming.

[0005] Therefore, the present disclosure has been made in consideration of the above points, and aims to provide a sentence generation device that can easily create sentences that show a person's tendencies. [Means for solving the problem]

[0006] The first aspect of the sentence generation device includes an answer extraction unit that extracts answer results for answer items to question items that meet a second condition from answer items included in the survey results for respondents that meet a first condition, among the answer results of a survey administered to a plurality of respondents, and a sentence generation unit that generates sentences that express the tendencies of respondents that meet the first condition, according to the answer results extracted by the answer extraction unit.

[0007] In addition, in the sentence generation device of the second aspect, the question item that meets the second condition is a question item for a characteristic answer item that has a unique response rate among the answer items in the questionnaire, and the sentence generation unit generates the sentence using words corresponding to the characteristic answer item.

[0008] In addition, in the sentence generation device of the third aspect, the characteristic answer item is an answer item for which the difference between the answer results of the questionnaire for respondents who meet the first condition and the average answer results of the questionnaire for respondents who meet a third condition different from the first condition is equal to or greater than a predetermined threshold.

[0009] In addition, in a fourth aspect of the sentence generation device, the second condition is that the question item is manually selected in advance.

[0010] In addition, the sentence generation device of the fifth aspect further includes a display unit that displays the sentence generated by the sentence generation unit and displays question items corresponding to the characteristic answer items used in sentence generation by the sentence generation unit.

[0011] In addition, in the sentence generation device of a sixth aspect, the display unit displays the comparison results of the question items as a graph.

[0012] In addition, the sentence generation device of the seventh aspect further includes an additional reception unit that receives, during or after the display of the sentence by the display unit, a selection of question items to be used in sentence generation by the sentence generation unit from among the question items corresponding to the characteristic answer items, and the sentence generation unit regenerates the sentence using words corresponding to the answer items to the question items selected through the additional reception unit, and the display unit displays the regenerated sentence.

[0013] Moreover, the sentence generation device of the eighth aspect includes an image generation unit that generates a face image of a respondent that matches the first condition from the sentence generated by the sentence generation unit. [Effects of the Invention]

[0014] According to the present disclosure, it is possible to provide a sentence generation device that can easily create sentences that show a person's tendencies. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a schematic block diagram of a sentence generation device according to an embodiment of the present disclosure. [Figure 2] FIG. 10 is an explanatory diagram illustrating an example of a questionnaire according to an embodiment of the present disclosure. [Figure 3] 1 is a block diagram illustrating an example of a functional configuration of a sentence generation device according to an embodiment of the present disclosure. [Figure 4] FIG. 10 is an explanatory diagram illustrating an example of a prompt according to an embodiment of the present disclosure. [Figure 5] FIG. 2 is an explanatory diagram illustrating an example of a display by a display unit according to an embodiment of the present disclosure. [Figure 6A] 10 is an explanatory diagram for explaining the scoring of the average of the response results of a target and a comparison subject according to an embodiment of the present disclosure. FIG. [Figure 6B] 10 is an explanatory diagram for explaining the scoring of the average of the response results of a target and a comparison subject according to an embodiment of the present disclosure. FIG. [Figure 6C] 10 is an explanatory diagram for explaining the scoring of the average of the response results of a target and a comparison subject according to an embodiment of the present disclosure. FIG. [Figure 6D] 10 is an explanatory diagram for explaining the scoring of the average of the response results of a target and a comparison subject according to an embodiment of the present disclosure. FIG. [Figure 7A] 10 is an explanatory diagram for explaining the scoring of the average of the response results of a target and a comparison subject according to an embodiment of the present disclosure. FIG. [Figure 7B] 10 is an explanatory diagram for explaining the scoring of the average of the response results of a target and a comparison subject according to an embodiment of the present disclosure. FIG. [Figure 7C] 10 is an explanatory diagram for explaining the scoring of the average of the response results of a target and a comparison subject according to an embodiment of the present disclosure. FIG. [Figure 7D] 10 is an explanatory diagram for explaining the scoring of the average of the response results of a target and a comparison subject according to an embodiment of the present disclosure. FIG. [Figure 8] 10 is a flowchart illustrating an example of the flow of a sentence generation process performed by a sentence generation device according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of the present invention will be described below with reference to the drawings. The same reference numerals are used throughout the drawings to designate identical or equivalent components and parts. The dimensional proportions of the drawings are exaggerated for the sake of clarity and may differ from the actual proportions.

[0017] An example of a sentence generation device 10 according to this embodiment will be described with reference to FIG. FIG. 1 is a block diagram showing the hardware configuration of a sentence generation device 10 according to this embodiment.

[0018] 1, a sentence generation device 10 according to this embodiment includes a CPU (Central Processing Unit) 101, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, a storage unit 104, an input unit 105, and a display device 106. Each component is connected to each other via a bus 107 so as to be able to communicate with each other.

[0019] The CPU 101 is a central processing unit that executes various programs and controls each part. That is, the CPU 101 reads programs from the ROM 102 or the storage unit 104, and executes the programs using the RAM 103 as a work area. The CPU 101 controls the above-mentioned components and performs various arithmetic processing according to the programs recorded in the ROM 102 or the storage unit 104. In this embodiment, the programs are stored in the ROM 102 or the storage unit 104.

[0020] The ROM 102 stores various programs and various data. The RAM 103 temporarily stores programs or data as a working area. The storage unit 104 is configured with an HDD (Hard Disk Drive) or an SSD (Solid State Drive) and stores various programs including an operating system and various data.

[0021] Here, the information stored in the storage unit 104 in this embodiment includes, for example, a sentence generation model and an image generation model. The sentence generation model is used by the sentence generation unit 112 described later. The sentence generation model is publicly known, for example, as disclosed in ChatGPT (https: / / openai.com / index / chatgpt / ), and therefore a detailed description thereof will be omitted. Such a sentence generation model is configured by a large language model (LLM). The image generation model is used by the image generation unit 113 described later. The image generation model is publicly known, for example, as disclosed in DALL-E3 (https: / / openai.com / index / dall-e-3 / ), and therefore a detailed description thereof will be omitted. Note that the sentence generation model and the image generation model are not limited to being stored in the storage unit 104, and may also be stored in another device, for example, a server device connected to the sentence generation device 10 via a network.

[0022] The information stored in the storage unit 104 includes questionnaire questions and answers.

[0023] In addition, the sentence generation model, the image generation model, and some or all of the questionnaire questions and answer results are not limited to being stored in the sentence generation device 10, but may also be stored in another device, such as a server device connected to the sentence generation device 10 via a network.

[0024] Here, an example of a questionnaire used in this embodiment will be described. As shown in the figure, the questionnaire includes various questions such as "occupation," "employment status," "individual annual income," "marital status," "highest level of education," "gender," "topics of interest," and "frequency of cooking." Answer candidates for each question are predetermined for each question, and respondents can answer the question by selecting an answer candidate. For example, as shown in FIG. 2, for the question "occupation," the answer candidates are predetermined as "clerical worker," "technical worker," "service worker," "executive," "unemployed," "pensioner," and "other." The questionnaire questions and answer candidates are not limited to those shown in FIG. 2 and may be other questions and answer candidates. In this embodiment, the questionnaire uses, for example, a "Comprehensive Consumer Survey," but is not limited thereto.

[0025] The input unit 105 includes a pointing device such as a mouse and a keyboard, and is used to input various types of information. The input unit 105 is used to input settings such as the first and third conditions described below.

[0026] The display device 106 is, for example, a liquid crystal display, and displays various types of information under the control of the CPU 101.

[0027] Next, the functional configuration realized by the sentence generation device 10 will be described. FIG. 3 is a block diagram showing an example of the functional configuration of the CPU 101 of the sentence generation device 10. As shown in FIG.

[0028] 3, the writing generation device 10 has, as its functional configuration, a reception unit 110, an answer extraction unit 111, a writing generation unit 112, an image generation unit 113, a display unit 114, and an additional reception unit 115. Each functional configuration is realized by the CPU 101 reading and executing a program stored in the ROM 102 or the storage unit 104. Here, the writing generation device 10 of this embodiment is a device that executes a process of concretely creating a persona, as a target person for marketing or the like, through writing.

[0029] (Reception unit 110) The receiving unit 110 receives a first condition and a third condition input by a user. Here, the first condition can be arbitrarily set by the user of the text generation device 10 and is a condition for determining a target persona for generating a persona. For example, the first condition may be a "health-conscious woman in her 60s." To extract respondents who meet the first condition, "a health-conscious woman in her 60s," from among the respondents to the questionnaire, the receiving unit 110 extracts "a health-conscious woman in her 60s" from the answers to one question item or from the answers to multiple question items. For example, the receiving unit 110 extracts keywords, such as "health," "60s," and "female," from the first condition, "a health-conscious woman in her 60s." The receiving unit 110 then extracts respondents who selected "health" for the question item "topic of interest" or whose answers to the question items contained the keyword "health," and who selected "60s" for the question item "age" and "female" for the question item "gender." The extraction of respondents is not limited to the above-mentioned manner, and may be performed in other manners. For example, respondents to a questionnaire may be clustered in advance based on the answers to questions (for example, a group that is particular about health, a group that likes to travel, etc.), and respondents may be extracted based on the results of the clustering.

[0030] The third condition can be arbitrarily set by the user of the text generation device 10 and determines a comparison target persona to be compared with the target persona for generating a persona. For example, the third condition may include "all respondents to the questionnaire," "women in their 60s" or "women" that include all of the first condition, "health-conscious women in their 60s," but exclude some of the first condition, "respondents other than those who meet the first condition," and "respondents who provided predetermined answers to specific questions" that are unrelated to the first condition. The accepting unit 110 then extracts respondents who meet this third condition from among the respondents to the questionnaire. Hereinafter, respondents who meet the first condition will be referred to as "targets," and respondents who meet the third condition will be referred to as "comparison targets."

[0031] Note that the receiving unit 110 is not limited to receiving the first and third conditions and extracting respondents who meet the conditions, but may also receive information on respondents extracted by another device of the sentence generation device 10.

[0032] The receiving unit 110 also receives candidate question items manually selected in advance by the user from among the questionnaire question items. Here, the candidate question items are candidate question items to be used when the sentence generating unit 112 generates a target person profile. Note that the candidate question items are not limited to those input by the user, and may be frequently used question items that have been stored in advance as candidates. The receiving unit 110 may also extract question items related to the first condition, such as question items including the keywords "health," "60s," and "female" extracted from the first condition "health-conscious woman in her 60s" input by the user.

[0033] (Answer extraction part 111) The answer extraction unit 111 extracts candidate question items received by the receiving unit 110 from the answer results of the questionnaire given to multiple respondents, and extracts answer results for answer items that meet a second condition from answer items included in the questionnaire results for respondents that meet a first condition. Here, the question items that meet the second condition are question items for characteristic answer items with a unique answer rate among the answer items of the questionnaire. In this embodiment, from among the candidate question items received by the receiving unit 110, answer items for which the difference between the average of the answer results of the questionnaire for respondents that meet the first condition and the average of the answer results of the questionnaire for respondents that meet a third condition different from the first condition is equal to or greater than a predetermined threshold are defined as characteristic answer items.

[0034] Specifically, the answer extraction unit 111 first extracts the target's answer results and the comparison target's answer results for the candidate question items received by the receiving unit 110 from the answer items included in the target's survey results. Then, the answer extraction unit 111 calculates a score for the average of the extracted target's answer results and the comparison target's answer results, and extracts answer items for which the difference in score is equal to or greater than a predetermined threshold as characteristic answer items to be used by the sentence generation unit 112 when generating a character image of the target. Here, the predetermined threshold can be set arbitrarily by the user. The scores will be described later with reference to FIGS. 6A, 6B, 6C, 6D, 7A, 7B, 7C, and 7D.

[0035] (Sentence generation section 112) The sentence generation unit 112 generates a sentence expressing the tendency of respondents who meet the first condition, based on the answer results extracted by the answer extraction unit 111. Specifically, the sentence generation unit 112 generates a sentence expressing the tendency of respondents who meet the first condition, using words corresponding to the characteristic answer items extracted by the answer extraction unit 111. That is, as shown in FIG. 4, the sentence generation unit 112 generates a prompt by adding the fixed phrases "instruction," "constraints," and "output format" to the characteristic answer items extracted by the answer extraction unit 111, and inputs the generated prompt into the sentence generation model. In the example shown in FIG. 4, the characteristic answer items are listed in the "# target" column. Here, the "# target" column includes answer items that are not characteristic answer items but are predetermined by the user and are always used. For example, "individual annual income," "gender," and "married couple's employment status" are set to be included in the "# target" column even if they do not fall under the characteristic answer items. That is, the sentence generation unit 112 generates a sentence using words corresponding to the characteristic answer items and the always used answer items. In this embodiment, the image of a person represented by a sentence generated by the sentence generation unit 112 is a persona that is the target of marketing. Note that the prompt is not limited to being used as is as generated by the sentence generation unit 112, and the user may be able to modify it as appropriate. The sentence generated by the sentence generation unit 112 may be able to be modified as appropriate by the user. The sentence generation unit 112 may also generate a prompt that creates a headline for the generated sentence with a number of characters specified by the user, thereby making it possible to create a headline while generating the sentence.

[0036] (Image generation unit 113) The image generation unit 113 generates a facial image of the respondent who meets the first condition from the sentence generated by the sentence generation unit 112. Specifically, the image generation unit 113 inputs the sentence generated by the sentence generation unit 112 into the image generation model described above. As a result, the image generation unit 113 generates a facial image representing the target person.

[0037] (Display section 114) The display unit 114 displays the sentences generated by the sentence generation unit 112 on the display device 106, and also displays question items corresponding to the characteristic answer items used in generating the sentences by the sentence generation unit 112. As described above, the user may be allowed to modify the displayed sentences as appropriate.

[0038] Thereafter, the display unit 114 displays, on the display device 106, the facial image generated by the image generation unit 113 and a graph of the comparison results between the question item and the relevant question item. Specifically, as shown in FIG. 5 , the display unit 114 displays, within the display area of ​​the display device 106, a sentence in the sentence display section S on the upper left, a facial image in the facial image display section T on the upper right, and a graph of the comparison results between the question item and the relevant question item in the graph display section U on the lower side. The display unit 114 also displays the heading of the sentence displayed in the sentence display section S in the heading display section V above the sentence display section S. Here, the display of the graph of the comparison results between the question items specifically displays data of the response results for question items such as "Marital Status," "Employment Status," and "Highest Educational Background," which are used when the sentence generation unit 112 generates a sentence and input to the sentence generation model, divided into target and comparison items. Note that the display of graphs for all question items is not limited to this, and it may be configured to display only question items whose scores are higher than a predetermined threshold. The display order of the graphs may be the order in which the sentence generation unit 112 used them to generate sentences, the order in which sentences related to the question items are written in the generated sentences, or the order in which the difference in scores is largest. The display unit 114 is not limited to displaying sentences generated by the sentence generation unit 112 on the display device 106, and may also execute a process of outputting sentences generated by the sentence generation unit 112 to another device connected to the sentence generation device 10 via a network.

[0039] Furthermore, the display unit 114 is not limited to displaying on the display device 106 the sentence generated by the sentence generation unit 112 and question items corresponding to the characteristic answer items used to generate the sentence by the sentence generation unit 112, and then displaying the facial image generated by the image generation unit 113 and a graph of the comparison results of the question items, but may also display the sentence, question items, facial image, and graph at the same time.

[0040] (Additional Reception Section 115) The additional accepting unit 115 accepts selection of question items to be used in sentence generation by the sentence generating unit 112 from among question items corresponding to characteristic answer items during or after the display of the sentence by the display unit 114. Then, the sentence generating unit 112 regenerates a prompt using words corresponding to answer items to the question items selected via the additional accepting unit 115, and regenerates a sentence using the prompt. Then, the display unit 114 displays the regenerated sentence on the display device 106.

[0041] Next, the process of averaging the target response results and the comparison response results will be described with reference to Figures 6A, 6B, 6C, 6D, 7A, 7B, 7C, and 7D.

[0042] FIG. 6A shows an example of the unprocessed questionnaire response results for a question item that allows multiple answers, such as "hobbies." For example, a respondent with ID "1111" is not included in the target (the "target" column is blank), is included in the comparison target (the "comparison target" column is marked "○"), and has a weighting of "0.9," indicating that the respondent answered "baseball" and "soccer" to the question item "hobbies." Also, a respondent with ID "2222" is included in the target (the "target" column is marked "○"), is included in the comparison target (the "comparison target" column is marked "○"), and has a weighting of "1," indicating that the respondent answered "baseball," "driving," and "hot springs" to the question item "hobbies." In the figure, a "1" is entered for the answer candidate selected by the respondent, and a "0" is entered for the answer candidate not selected by the respondent. Here, the weighting is a value that can be set by the user and is a value that corrects the survey response results for population bias.

[0043] Figure 6B shows the result of converting the "0" representing the unselected answer candidate in Figure 6A into "-1", because a weight back cannot be applied to "0".

[0044] Figure 6C is a diagram in which the results of Figure 6B are aggregated with weighting. That is, the numerical values ​​in the answer column of Figure 6B ("1" or "-1") are multiplied by the weighting, and the resulting values ​​are substituted for the numerical values ​​in the answer column and aggregated. For example, for respondent ID "1111," the baseball "1," soccer "1," driving "-1," and hot springs "-1" in Figure 6B are each multiplied by the weighting "0.9," and the results are aggregated as baseball "0.9," soccer "0.9," driving "-0.9," and hot springs "-0.9."

[0045] FIG. 6D is a diagram showing the aggregated scores from FIG. 6C. Specifically, for the "target average," the average of the answer columns for respondent IDs "2222" and "3333" marked with a "○" in the "target" column in FIG. 6C is aggregated. For example, for "baseball," the average is calculated as "1.1," which is the average of the "1" for respondent ID "2222" and the "1.2" for respondent ID "3333." For "soccer," the average is calculated as "-1.1," which is the average of the "-1" for respondent ID "2222" and the "-1.2" for respondent ID "3333." For the "comparison average," the average is calculated as "1111," "2222," "3333," "4444," and "5555," which are marked with a "○" in the "comparison" column in FIG. 6C. For example, for "baseball," the average of "0.9" for respondent ID "1111," "1" for respondent ID "2222," "1.2" for respondent ID "3333," "-1.3" for respondent ID "4444," and "-0.8" for respondent ID "5555" is calculated as "0.2." For "soccer," the average of "0.9" for respondent ID "1111," "-1" for respondent ID "2222," "-1.2" for respondent ID "3333," "1.3" for respondent ID "4444," and "0.8" for respondent ID "5555" is calculated as "0.16." For "difference," the difference between the calculated "target average" and the "comparison average" is calculated. For example, for "baseball," the difference between the target average of "1.1" and the comparison target average of "0.2" is calculated as "0.9." For "soccer," the difference between the target average of "-1.1" and the comparison target average of "0.16" is calculated as "-1.26." The answer extraction unit 111 extracts answer items whose "difference" is equal to or greater than a predetermined threshold as characteristic answer items to be used by the sentence generation unit 112 when generating a character profile of the target. Here, if the difference is a "+ (plus)" value, the characteristic answer item portion of the sentence generated by the sentence generation unit 112 will be written in a positive manner (e.g., "does ~," "likes ~," "is high in ~," etc.), and if the difference is a "- (minus)" value, the characteristic answer item portion of the sentence generated by the sentence generation unit 112 will be written in a negative manner (e.g., "does not ~," "avoids ~," "is low in ~," etc.).Furthermore, when the content of a question item is a negative description (for example, "I don't like doing ~"), if the difference is a "+ (plus)" value, the feature answer item part of the sentence generated by the sentence generation unit 112 will be a negative description (for example, "I don't do ~", "Avoid ~", "Low ~", etc.), and when the difference is a "- (minus)" value, the feature answer item part of the sentence generated by the sentence generation unit 112 will be a positive description (for example, "I do ~", "Prefer ~", "High ~", etc.). Note that when there are multiple answer items whose differences are equal to or greater than a predetermined threshold, the sentence generation unit 112 may generate a sentence using all feature answer items whose differences are equal to or greater than the predetermined threshold, or may generate a sentence using only the feature answer item whose difference value is the largest, or may generate a sentence using only the difference of a magnitude of a rank predetermined by a user setting.

[0046] FIG. 7A shows an example of unprocessed survey responses to a question item, such as "I like luxury brands," for which only one answer can be entered, where the answer candidates have different levels of degree, such as "1: Very applicable," "2: Somewhat applicable," "3: Not very applicable," and "4: Not applicable at all." For example, respondent ID "1111" is not included in the target (the "target" field is blank), but is included in the comparison target (the comparison target field is marked with "○"), with a weighting of "0.9," indicating that the respondent answered "Very applicable" to the question item "I like luxury brands." Also, respondent ID "2222" is not included in the target (the "target" field is blank), but is included in the comparison target (the comparison target field is marked with "○"), with a weighting of "1," indicating that the respondent answered "Somewhat applicable" to the question item "I like luxury brands." In FIG. 7A, "1" is entered for answer candidates selected by the respondent, and "0" is entered for answer candidates not selected by the respondent.

[0047] Figure 7B is a diagram in which the "0" representing the unselected answer candidate in Figure 7A is converted to "-1", because a weight back cannot be applied to "0".

[0048] Figure 7C is a diagram where the results of Figure 7B are tabulated with weighting. That is, the numerical values ​​in the answer column of Figure 7B ("1" or "-1") are multiplied by the weighting, and the resulting values ​​are substituted for the numerical values ​​in the answer column and tabulated. For example, for respondent ID "1111," the values ​​in Figure 7B for "very applicable" ("1"), "somewhat applicable" ("-1"), "not very applicable" ("-1"), and "not at all applicable" ("-1") are each multiplied by a weighting of "0.9," and are tabulated as "very applicable" ("0.9"), "somewhat applicable" ("-0.9"), "not very applicable" ("-0.9"), and "not at all applicable" ("-0.9")

[0049] FIG. 7D is a diagram showing the aggregated scores of FIG. 7C. Specifically, for the "target average," the average of the response columns for respondent IDs "2222," "3333," "6666," "7777," and "8888" marked with a "○" in the "target" column of FIG. 7C is aggregated. For example, for "strongly applicable," the average of "-1" for respondent ID "2222," "-1.2" for respondent ID "3333," "-0.9" for respondent ID "6666," "-1" for respondent ID "7777," and "-1.2" for respondent ID "8888" is aggregated as "-1.06." For "somewhat applicable," the average of "1" for respondent ID "2222," "-1.2" for respondent ID "3333," "0.9" for respondent ID "6666," "-1" for respondent ID "7777," and "-1.2" for respondent ID "8888" is calculated as "-0.3." For the "average of comparisons," the average of the response columns for respondent IDs "1111," "2222," "3333," "4444," "5555," "6666," "7777," "8888," and "9999," which have "○" in the "comparison" column in Figure 7C, is calculated. For example, for "Very applicable," the average of "0.9" for respondent ID "1111," "-1" for respondent ID "2222," "-1.2" for respondent ID "3333," "-1.3" for respondent ID "4444," "0.8" for respondent ID "5555," "-0.9" for respondent ID "6666," "-1" for respondent ID "7777," "-1.2" for respondent ID "8888," and "1.3" for respondent ID "9999" is calculated as "-0.4." For "somewhat applicable," the average of "-0.9" for respondent ID "1111," "1" for respondent ID "2222," "-1.2" for respondent ID "3333," "-1.3" for respondent ID "4444," "-0.8" for respondent ID "5555," "0.9" for respondent ID "6666," "-1" for respondent ID "7777," "-1.2" for respondent ID "8888," and "-1.3" for respondent ID "9999" is calculated as "-0.64." For "difference," the difference between the calculated "target average" and the "comparison average" is calculated.For example, for "very applicable," the difference between the target average of "-1.06" and the comparison target average of "-0.4" is calculated as "-0.66." For "somewhat applicable," the difference between the target average of "-0.3" and the comparison target average of "-0.64" is calculated as "0.34." The answer extraction unit 111 extracts answer items whose "difference" is equal to or greater than a predetermined threshold as characteristic answer items to be used by the sentence generation unit 112 when generating a person profile of the target. Here, if the difference is a "+ (plus)" value, the characteristic answer item portion of the sentence generated by the sentence generation unit 112 will be written in a positive manner (e.g., "does ~," "prefers ~," "is high in ~," etc.), and if the difference is a "- (minus)" value, the characteristic answer item portion of the sentence generated by the sentence generation unit 112 will be written in a negative manner (e.g., "does not ~," "avoids ~," "is low in ~," etc.). Furthermore, when the content of a question item is a negative description (for example, "I don't like doing ~"), if the difference is a "+ (plus)" value, the feature answer item part of the sentence generated by the sentence generation unit 112 will be a negative description (for example, "I don't do ~", "Avoid ~", "Low ~", etc.), and when the difference is a "- (minus)" value, the feature answer item part of the sentence generated by the sentence generation unit 112 will be a positive description (for example, "I do ~", "Prefer ~", "High ~", etc.). Note that when there are multiple answer items whose differences are equal to or greater than a predetermined threshold, the sentence generation unit 112 may generate a sentence using all feature answer items whose differences are equal to or greater than the predetermined threshold, or may generate a sentence using only the feature answer item whose difference value is the largest, or may generate a sentence using only the difference of a magnitude of a rank predetermined by a user setting.

[0050] Next, the operation of the writing generation device 10 will be described with reference to Fig. 8. Fig. 8 is a flowchart showing an example of the flow of writing generation processing by the writing generation device 10. The processing is performed by the CPU 101 reading a program from the ROM 102 or the storage unit 104, expanding it, and executing it. Furthermore, as a premise of this flowchart, the writing generation device 10 stores questionnaire question items and answer results in the storage unit 104.

[0051] In step S100, the CPU 101 (receiving unit 110) of the writing generation device 10 receives a first condition, which is a condition for determining a target character image for generating a persona, and a third condition, which is a condition for determining a comparison character image to be compared with the target character image for generating a persona. Then, the process proceeds to the next step S101.

[0052] In step S101, the CPU 101 (reception unit 110) of the text generation device 10 extracts respondents who satisfy the first condition and respondents who satisfy the third condition from the respondents to the questionnaire, and then proceeds to the next step S102.

[0053] In step S102, the CPU 101 (reception unit 110) of the sentence generation device 10 receives candidate question items that have been manually selected in advance by the user from among the question items of the questionnaire, and then the process proceeds to the next step S103.

[0054] In step S103, the CPU 101 (answer extraction unit 111) of the sentence generation device 10 converts the average of the questionnaire response results for the target and the comparison subject from the candidate question items received in step S102 into scores, calculates the difference, and extracts characteristic answer items whose difference is equal to or greater than a predetermined threshold value. Then, the process proceeds to the next step S104.

[0055] In step S104, the CPU 101 (sentence generation unit 112) of the sentence generation device 10 generates a prompt using the characteristic answer items extracted in step S103 and a predetermined fixed phrase, and then proceeds to the next step S105.

[0056] In step S105, the CPU 101 (sentence generation unit 112) of the sentence generation device 10 inputs the prompt generated in step S104 into the sentence generation model, and then proceeds to the next step S106.

[0057] In step S106, the CPU 101 (sentence generation unit 112) of the sentence generation device 10 generates sentences expressing the tendency of the target using the sentence generation model, and then the process proceeds to the next step S107.

[0058] In step S107, the CPU 101 (image generation unit 113) of the text generation device 10 generates a facial image representing the target person's image based on the text generated in step S106. Here, the facial image may be generated when an input for generating a facial image is received from the user, or the CPU 101 (image generation unit 113) may generate the facial image regardless of the user's input. Then, the process proceeds to the next step, S108.

[0059] In step S108, the CPU 101 (display unit 114) of the sentence generation device 10 displays the sentence generated in step S106, a graph of the comparison result of the question items corresponding to the characteristic answer items used in sentence generation by the sentence generation unit 112, and the face image generated in step S107 on the display device 106 (see FIG. 5). Then, the process ends.

[0060] Although not shown, during or after the display of the sentence by the display unit 114, the sentence generation unit 112 may accept a selection of question items to be used in sentence generation from among question items corresponding to characteristic answer items. In this case, the sentence generation unit 112 regenerates a sentence using words corresponding to answer items to the question items selected via the addition acceptance unit 115, and the display unit 114 displays the regenerated sentence on the display device 106. Furthermore, the image generation unit 113 generates a face image representing the portrait of the target based on the regenerated sentence.

[0061] According to this embodiment, it is possible to easily create text that shows the tendencies of people who are the target of marketing. In other words, when analyzing the profile of a target person in marketing, personas are created, but this is done based on the user's experience and intuition, which is a heavy burden and has problems such as large variations in accuracy. This embodiment makes it possible to solve these problems.

[0062] The present disclosure is not limited to the above-described embodiments, and various modifications other than those described above are possible without departing from the spirit of the present disclosure.

[0063] The characteristic answer items are not limited to being extracted from answer items whose difference is equal to or greater than a predetermined threshold by comparing scores as described above, but may be extracted by other methods or by combining a plurality of methods. For example, if the answer items are expressed numerically, such as annual income or age, the average values ​​of the target and comparison subject may be compared, and characteristic answer items may be extracted from answer items whose difference is equal to or greater than a predetermined threshold.

[0064] Furthermore, extraction of characteristic answer items may be performed using machine learning. Specifically, a model is constructed as a "discrimination problem" in which the answer numbers of the answer candidates for all question items in the questionnaire are used as explanatory variables (for example, values ​​1 to 7 (see Figure 2)), and whether the respondent who selected the answer candidate is the target or a comparison target is used as the objective variable. Then, explanatory variables (question items) derived when constructing such a model may be extracted as characteristic answer items with high importance.

[0065] In addition, a model may be constructed that learns the target's response results, the comparison target's response results, and the characteristic response items, and by inputting the target's response results and the comparison target's questionnaire and response data, it may be possible to extract the characteristic response items.

[0066] The present disclosure can also be applied to a program. In the above embodiment, the program is pre-stored (installed) in ROM 102 or storage unit 104, but the present disclosure is not limited to this. The program may be provided in a form recorded on a recording medium such as a CD-ROM (Compact Disk Read Only Memory), a DVD-ROM (Digital Versatile Disk Read Only Memory), or a USB (Universal Serial Bus) memory. The program may also be downloaded from an external device via a network.

[0067] The program of the present disclosure can be provided as a program product. The program product includes any product for providing the program. For example, the program product includes a program provided over a network such as the Internet, and a non-transitory computer-readable recording medium such as a CD-ROM or DVD on which the program is stored.

[0068] The following supplementary notes are further provided regarding one embodiment of the technology disclosed in the present application.

[0069] (Appendix 1) an answer extraction unit that extracts answer results of answer items to question items that meet a second condition from answer items included in the survey results of respondents that meet a first condition, among the survey response results given to a plurality of respondents; a sentence generation unit that generates a sentence expressing the tendency of respondents who meet the first condition according to the answer results extracted by the answer extraction unit; A sentence generation device comprising:

[0070] (Appendix 2) The question item that meets the second condition is a question item for a characteristic answer item that has a unique answer ratio among the answer items of the questionnaire, The sentence generation device according to claim 1, wherein the sentence generation unit generates the sentence using words corresponding to the characteristic answer items.

[0071] (Appendix 3) The sentence generation device described in Appendix 2, wherein the characteristic answer item is an answer item for which the difference between the answer results of the questionnaire for respondents who meet the first condition and the average answer results of the questionnaire for respondents who meet a third condition different from the first condition is greater than a predetermined threshold.

[0072] (Appendix 4) 4. The sentence generation device according to claim 1, wherein the second condition is that the question item is manually selected in advance.

[0073] (Appendix 5) The sentence generation device according to claim 2 or 3, further comprising a display unit that displays the sentence generated by the sentence generation unit and also displays question items corresponding to the characteristic answer items used in generating the sentence by the sentence generation unit.

[0074] (Appendix 6) 6. The sentence generation device according to claim 5, wherein the display unit displays the comparison result of the question items as a graph.

[0075] (Appendix 7) The system further includes an additional reception unit that receives selection of question items to be used in sentence generation by the sentence generation unit from among question items corresponding to the characteristic answer items during or after display of the sentence by the display unit, the sentence generation unit regenerates a sentence using words corresponding to answer items to the question items selected through the addition reception unit; 7. The text generation device according to claim 5, wherein the display unit displays the regenerated text.

[0076] (Appendix 8) A text generation device according to any one of Supplementary Note 1 to Supplementary Note 7, comprising an image generation unit that generates a facial image of a respondent that meets the first condition from the text generated by the text generation unit. [Explanation of symbols]

[0077] 10 Sentence generator 111 Answer extraction part 112 Sentence generation section 113 Image Generation Unit 114 Display section 115 Additional Reception Department

Claims

1. an answer extraction unit that extracts answer results of answer items to question items that meet a second condition from answer items included in the survey results of respondents that meet a first condition among the survey response results given to a plurality of respondents; a sentence generation unit that generates a sentence expressing the tendency of respondents who meet the first condition in accordance with the answer results extracted by the answer extraction unit; A sentence generation device comprising:

2. The question item that meets the second condition is a question item for a characteristic answer item having a unique answer ratio among the answer items of the questionnaire, The sentence generation device according to claim 1 , wherein the sentence generation unit generates the sentences using words corresponding to the characteristic answer items.

3. 3. The sentence generation device according to claim 2, wherein the characteristic answer item is an answer item for which the difference between the answer results of the questionnaire for respondents who meet the first condition and the average answer results of the questionnaire for respondents who meet a third condition different from the first condition is greater than or equal to a predetermined threshold.

4. The sentence generation device according to claim 1 , wherein the second condition is that the question item is manually selected in advance.

5. 3. The sentence generation device according to claim 2, further comprising a display unit that displays the sentence generated by the sentence generation unit and also displays question items corresponding to the characteristic answer items used in generating the sentence by the sentence generation unit.

6. The sentence generation device according to claim 5 , wherein the display unit displays the comparison results of the question items as a graph.

7. The system further includes an additional reception unit that receives selection of question items to be used in sentence generation by the sentence generation unit from among question items corresponding to the characteristic answer items during or after display of the sentence by the display unit, the sentence generation unit regenerates a sentence using words corresponding to answer items to the question items selected through the addition reception unit; 7. The text generation device according to claim 5, wherein the display unit displays the regenerated text.

8. 2. The text generation device according to claim 1, further comprising an image generation unit that generates a face image of a respondent who meets the first condition from the text generated by the text generation unit.

Images